Openai Realtime Voice

Build production OpenAI Realtime voice agents and low-latency spoken interactions with live audio sessions, WebRTC or WebSocket transport, voice activity detection, tool/function calling, prompt design, logging, consent, privacy, safety, latency, and cost controls. Use for speech-to-speech agents and live voice UX; do not use for separate request-based transcription, text-to-speech, or offline audio generation work.

246 stars 50 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add calesthio/generative-media-skills --skill openai-realtime-voice
Manual install
git clone --depth 1 https://github.com/calesthio/generative-media-skills.git /tmp/generative-media-skills
mkdir -p ~/.claude/skills
cp -r /tmp/generative-media-skills/skills/providers/voice-agents/openai-realtime-voice ~/.claude/skills/openai-realtime-voice

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# OpenAI Realtime voice

Use this skill when the deliverable is a live spoken interaction: a browser voice assistant, phone-like agent, low-latency speech-to-speech support flow, guided interview, tutoring conversation, live kiosk, or realtime voice UI that listens, reasons, speaks, interrupts, and may call tools.

Do not use this skill for batch speech-to-text, offline TTS, voiceover generation, audio editing, dubbing, music, or file-based audio tasks. Those belong to the separate OpenAI audio/request APIs or other speech/audio skills. The boundary is simple: if a persistent realtime session and turn-taking behavior are part of the product, use this skill; if the job is "turn this file/text into text/audio," do not.

All OpenAI API facts below were verified against first-party OpenAI documentation on 2026-07-10. Re-check model identifiers, prices, session limits, voices, API object fields, data retention, and policy requirements before production release because Realtime surfaces change quickly.

## Source-grounded facts to carry into every design

Documented facts:

- OpenAI positions Realtime sessions as best for live audio that needs low latency; request-based audio APIs are best for files, bounded requests, or generated speech that does not need a live session. Source: [Realtime and audio overview](https://developers.openai.com/api/docs/guides/realtime).
Read the full skill on GitHub

Details

Skill name
openai-realtime-voice
Path
skills/providers/voice-agents/openai-realtime-voice/SKILL.md
License
MIT
Repo updated
14 July 2026

FAQ

What does the Openai Realtime Voice skill do?

Build production OpenAI Realtime voice agents and low-latency spoken interactions with live audio sessions, WebRTC or WebSocket transport, voice activity detection, tool/function calling, prompt design, logging, consent, privacy, safety, latency, and cost controls. Use for speech-to-speech agents and live voice UX; do not use for separate request-based transcription, text-to-speech, or offline audio generation work.

How do I install the Openai Realtime Voice skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add calesthio/generative-media-skills --skill openai-realtime-voice. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Openai Realtime Voice popular?

It lives in calesthio/generative-media-skills, which has 246 GitHub stars and 50 forks.

Related skills

2d Character Rig Animation

246

calesthio/generative-media-skills

Production guidance for reusable layered 2D character rigs in browser-rendered and video media. Use for SVG hierarchies, pivots and constraints, FK/IK planning, pose and facial libraries, acting, cycles, deterministic handoff, crop variants, and rig QA; not for character concept continuity, 3D armatures, or motion-capture solving.

Frontend & Design50

3d Asset Production

246

calesthio/generative-media-skills

Use this skill to turn generated, captured, scanned, or modeled 3D output into production-ready standalone assets for DCC, real-time engine, web, or interchange delivery. It covers requirements, topology repair, scale and axes, UVs, PBR baking, LODs, static and skeletal readiness, rig handoff, optimization, glTF/USD/FBX delivery, validation, QA, and rights/provenance. Do not use it for provider-specific generation prompts, full scene/world building, mocap operation, or exact CAD/manufacturing work.

Images, Video & Audio50

Ace Step

246

calesthio/generative-media-skills

Use ACE-Step and ACE-Step 1.5 for local or hosted AI music generation, including text-to-music, lyrics-to-song, instrumental beds, covers, repainting, stem/track extraction, track completion, LoRA personalization, REST/Python/Gradio workflows, rights review, and music integration for video, ads, games, and social content.

Images, Video & Audio50

Performance Direction

246

calesthio/generative-media-skills

Provider-independent performance direction for generated video, avatar/spokesperson clips, animation, ads, film scenes, social content, and voice-led media. Use when an agent must cast or direct synthetic performers, avatars, animated characters, talking heads, AI video characters, or voice performances; plan acting beats, objective/obstacle/action, blocking, gesture, eye-line, facial expression, body language, lip-sync, voice alignment, rehearsal prompts, iteration, continuity, consent, and performance QA.

Images, Video & Audio50

Openai Audio

246

calesthio/generative-media-skills

Produce and understand audio with OpenAI request-based audio APIs and audio-capable chat models, including text-to-speech, transcription, translation, multimodal audio input/output, model routing, prompt and performance direction, artifact custody, approval gates, and safety/rights review. Use for non-realtime OpenAI audio production; route continuous live voice agents to the separate realtime voice skill.

Images, Video & Audio50

Pika Video

246

calesthio/generative-media-skills

Produce short-form video with Pika (pika.art) — its effect-driven tools (Pikaffects, Pikadditions, Pikaswaps, Pikaframes, Pikascenes, Pikatwists) and audio-driven lip sync (Pikaformance), plus text-to-video and image-to-video. Use when a task calls for playful, stylized, meme-able social clips, or for applying generative effects and object swaps to real uploaded footage, and when deciding whether Pika is the right engine versus a higher-fidelity model. Covers model versions, credit/plan economics, the fal.ai API route, prompt construction, iteration/repair, capability limits, and consent/right

Images, Video & Audio50

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.